Avoiding Unintended AI Behaviors (Hibbard)

Added by Deon Garrett about 6 years ago

Artificial intelligence (AI) systems too complex for predefined environment models and actions will need to learn environment models and to choose actions that optimize some criteria. Several authors have described mechanisms by which such complex systems may behave in ways not intended in their designs. This paper describes ways to avoid such unintended behavior. For hypothesized powerful AI systems that may pose a threat to humans, this paper proposes a two-stage agent architecture that avoids some known types of unintended behavior. For the first stage of the architecture this paper shows that the most probable finite stochastic program to model a finite history is finitely computable, and that there is an agent that makes such a computation without any unintended instrumental actions.

paper_56.pdf (156.5 kB)


Replies (3)

RE: Avoiding Unintended AI Behaviors (Hibbard) - Added by fuzail faisal 27 days ago

thanks this is good blog. "אוליב על המים"https://www.blik.co.il/Brands/BrandsOlive.aspx

RE: Avoiding Unintended AI Behaviors (Hibbard) - Added by Saqib 12 8 days ago

They always delivered, even if we had impossible things that we needed them to do. Their Dental Directory is good too. They worked long hours to keep the project running smoothly.

RE: Avoiding Unintended AI Behaviors (Hibbard) - Added by Sk production about 10 hours ago

thanks for a few adjunct informative weblog. in which else ought to I gather that form of auspices written in such a really perfect manner? i have a task that Im simply now running regarding, and i have been at the see out for such recommendation.gree inverter ac 1 ton

(1-3/3)